JP2023540813A - Robot guidance management between zones within the environment - Google Patents

Abstract

A server configured to define a first zone and an adjacent second zone in an environment, a sill along a boundary between the first zone and the second zone, and a waypoint associated with the sill. A system and method for robot guidance management are provided. One or more autonomous robots in communication with the server determine a route from a first zone to a second zone, including waypoints, across the threshold, and determine the waypoints in conjunction with crossing the threshold. The robot is configured to guide the robot along a route from the first zone to the second zone, including passing through.

Description

This application claims the benefit of priority to U.S. Patent Application No. 17/017,801, filed September 11, 2020, and is incorporated herein by reference.

TECHNICAL FIELD This invention relates to robot guidance and, more particularly, to robot guidance management within an environment having multiple distinct areas or zones.

Ordering products over the Internet and having them delivered to your home is a very popular shopping method. Fulfilling such orders in a timely, accurate, and efficient manner is logistically difficult, to say the least. Clicking the "Check Out" button in the virtual shopping cart creates an "Order." An order includes a list of items to be shipped to a particular address. The process of "fulfilment" includes physically removing or "picking" these items from a large warehouse, packaging the items, and shipping the items to a specified address. Therefore, an important goal of the order fulfillment process is to ship as many items as possible in as little time as possible.

The order fulfillment process typically takes place in a large warehouse that houses many products, including those listed in the order. Thus, among the tasks of order fulfillment is the task of navigating the warehouse to locate and collect the various items listed in the order. In addition, products that are ultimately to be shipped must first be received at a warehouse and stored or "arranged" in storage bins in an orderly manner throughout the warehouse, so that the products are easily placed for shipment. can be taken out.

In large warehouses, the products being shipped and ordered may be warehoused very far apart from each other and distributed among many other products. Order fulfillment processes that use only human workers to place and pick items require the workers to walk for long periods of time, which can be inefficient and time-consuming. Since the efficiency of the fulfillment process is a function of the number of items shipped per unit time, increasing time reduces efficiency.

To increase efficiency, robots can be used to perform human functions or to supplement human activities. A robot may be assigned, for example, to "place" multiple items at various locations distributed throughout the warehouse, or to "pick" items from various locations for packing and shipping. Picking and placement can be performed by the robot alone or with the aid of a human operator. For example, in a picking task, a human worker picks an item from a shelf and places it on a robot, or in a placement task, a human worker picks an item from a robot and places the item on a shelf. It will be placed.

Some warehouses or other environments are divided into various distinct areas. For example, some products may require temperature control and are therefore placed in a temperature-controlled area, such as a freezer. Some products may require a higher level of security and are therefore placed in an area separated by a barrier from other products. Some environments have areas at various heights that are accessible by sloped floors or elevators. Some different areas may be separated by physical barriers, such as walls, while other different areas may not have physical barriers separating the areas. Navigating between such areas can cause inefficient routing or congestion between multiple robots or between robots and human workers.

U.S. Patent Application No. 15/807,672 U.S. Patent Application No. 15/254,321 U.S. Patent No. 10,386,851 U.S. Patent No. 10,429,847 U.S. Patent No. 10,513,033

Sebastian Thrun, “Robotic Mapping: A Survey,” Carnegie-Mellon University, CMU-CS-02-111, February 2002

A method and system for guiding and managing a robot in an environment or guiding space having multiple zones is provided herein.

In one aspect, a method is provided for guiding an autonomous robot from a first zone to an adjacent second zone within an environment. The method defines, by a server, a first zone and a second zone in an environment, a threshold along a boundary between the first zone and the second zone, and a waypoint associated with the threshold. determining a route for the autonomous robot from a first zone to a second zone that crosses the threshold, the route including waypoints; The method includes guiding the robot along a route from the first zone to the second zone, including passing through waypoints in conjunction with traversing. In some embodiments, the waypoint is defined by a waypoint pose, and determining the route includes determining a route segment to the waypoint pose. Passing through the waypoint may include passing through the waypoint pose without pausing at the waypoint pose, or pausing at the waypoint pose before crossing the threshold. can. The waypoint may be located at a distance from the sill or on a border along the sill.

In some embodiments, the method further includes defining, by the server, a second waypoint associated with the sill, the waypoint and the second waypoint being located on opposite sides of the sill. In some embodiments, the boundary between two adjacent zones is a physical barrier, and the sill is located at an opening in the physical barrier. In some embodiments, the boundary between two adjacent zones is a virtual barrier, and the threshold is a location defined along the virtual barrier. In some embodiments, the method further includes defining, by the server, a second threshold along a boundary between adjacent zones, a second waypoint associated with the second threshold. In some embodiments, the method includes defining, by the server, a threshold that allows passage of the robot in a first direction; and defining a threshold opposite the first direction along a boundary between adjacent zones. defining a second threshold that allows passage of the robot in the direction of the robot.

In some embodiments, the method further includes the step of the robot joining a queue of robots waiting to pass through the threshold. In some embodiments, the method further includes the robot detecting an obstacle at the threshold using a camera, laser detector, or radar detector, or a combination thereof. In some examples, each of the zones is a secure area, a temperature-controlled area, a warehouse area, or an area at a different height than adjacent areas, or a combination thereof.

In a further aspect, a system is provided for guiding an autonomous robot from a first zone to an adjacent second zone within an environment. The system is configured to define a first zone and a second zone in the environment, a threshold along a boundary between the first zone and the second zone, and a waypoint associated with the threshold. an autonomous robot in communication with the server, the robot comprising a processor and a memory, the memory, when executed by the processor, directs the robot from a first zone to a second zone across a threshold including a waypoint; memorize instructions for guiding the robot along a route from a first zone to a second zone, including passing through waypoints in conjunction with crossing thresholds; . In some embodiments, the waypoint is defined by a waypoint pose, and the memory further stores instructions that, when executed by the processor, cause the autonomous robot to determine a route segment to the waypoint pose. do. In some embodiments, the memory, when executed by the processor, causes the robot to move through the waypoint pose without pausing at the waypoint pose or before crossing the threshold. Further memorize the command to pause at the pose. In some embodiments, the waypoint is located at a distance from the sill or on a border along the sill. In some examples, the server is configured to define a second waypoint associated with the sill, and the waypoint and the second waypoint are located on opposite sides of the sill.

In some embodiments, the boundary between two adjacent zones is a physical barrier, and the sill is located at an opening in the physical barrier. In some embodiments, the boundary between two adjacent zones is a virtual barrier, and the threshold is a location defined along the virtual barrier. In some examples, the server is configured to define a second threshold along a boundary between adjacent zones and a second waypoint associated with the second threshold. In some embodiments, the robot guidance server defines a threshold that allows passage of the robot in a first direction and also defines a threshold along a boundary between the first zone and the second zone. The second threshold is configured to define a second threshold that allows passage of the robot in a direction opposite to the first direction.

In some embodiments, the memory further stores instructions that, when executed by the processor, cause the autonomous robot to join a queue of robots waiting to pass through the threshold. In some embodiments, the memory includes instructions that, when executed by the processor, cause the autonomous robot to detect obstacles at the threshold using a camera, a laser detector, or a radar detector, or a combination thereof. further memorize.

In some examples, each of the zones is a secure area, a temperature-controlled area, a warehouse area, or an area at a different height than adjacent areas, or a combination thereof. In some embodiments, the server comprises one or more of a warehouse management system, an order server, a stand-alone server, a distributed system comprising memory for at least two of the plurality of robots, or a combination thereof. Be prepared for more.

These and other features of the invention will become apparent from the following detailed description and accompanying drawings.

FIG. 2 is a top view of an order fulfillment warehouse. 2 is a front view of the base of one of the robots used in the warehouse shown in FIG. 1. FIG. 2 is a perspective view of the base of one of the robots used in the warehouse shown in FIG. 1; FIG. Figure 2B is a perspective view of the robot of Figures 2A and 2B equipped with an armature and parked in front of the shelf shown in Figure 1; 2 is an illustration of a partial map of the warehouse of FIG. 1 created using a robot's laser radar; FIG. 2 is a flowchart illustrating a process for locating fiducial markers distributed throughout a warehouse and storing poses of the fiducial markers. This is a table in which reference identification indicators are mapped to poses. FIG. 3 is a table mapping box locations to reference identifications. FIG. 2 is a flow diagram illustrating a process for mapping product SKUs to poses. FIG. 1 is a configuration diagram of an embodiment of a robot system used in the method and system of the present invention. 1 is a diagram of a map of an environment divided into multiple zones; FIG. FIG. 1 is a block diagram of an exemplary computer processing system. 1 is a network diagram of an example distributed network; FIG.

The details of the present disclosure and its various features and advantages are described more fully with reference to the non-limiting examples and examples that are illustrated and/or illustrated in the accompanying drawings and detailed in the description below. The features illustrated in the drawings are not necessarily drawn to scale, and those skilled in the art will recognize features of one embodiment, even if not explicitly stated herein. Note that it can be used with other embodiments. Descriptions of well-known components and processing techniques may be omitted so as not to unnecessarily obscure the embodiments of the present disclosure. The examples used herein are merely intended to facilitate understanding of the manner in which the present disclosure may be practiced and to further enable those skilled in the art to practice the embodiments of the present disclosure. There is. Accordingly, the illustrations and examples herein should not be construed as limiting the scope of the disclosure. Additionally, it is noted that like reference numbers represent like parts throughout the several views of the drawings.

TECHNICAL FIELD The present invention relates to robot guidance management. Although not limited to any particular robot application, one suitable application in which the present invention may be used is order fulfillment. We will describe the use of robots in this application and provide context regarding robot guidance and management, but are not limited to this application.

Referring to FIG. 1, a typical order fulfillment warehouse 10 includes shelves 12 filled with various items that may be included in an order. In operation, an incoming stream of orders 16 from warehouse management server 15 arrives at order server 14 . Order server 14 may prioritize and group orders for assignment to robots 18 during the guidance process, among other things. When the robot is guided by an operator at a processing station (eg, station 100), orders 16 are assigned to robot 18 and communicated wirelessly for execution. The order server 14 may be a separate server with a separate software system configured to interoperate with the warehouse management system server 15 and the warehouse management software, or the functionality of the order server may be integrated into the warehouse management software. Those skilled in the art will appreciate that the warehouse management server 15 may be integrated with the warehouse management server 15 and run on the warehouse management server 15.

In a preferred embodiment, the robot 18 shown in FIGS. 2A and 2B includes an autonomous wheeled base 20 that includes a laser radar 22. The robot 18 shown in FIGS. Base 20 also features a transceiver (not shown) that enables robot 18 to receive commands and transmit data from order server 14 and/or other robots, and a pair of digital optical cameras 24a and 24b. shall be. The robot base also includes a charging port 26 for recharging the battery that powers the autonomous wheeled base 20. Base 20 further features a processor (not shown) that receives data from laser radar and cameras 24a and 24b to capture information representative of the robot's environment. As shown in FIG. 3, a memory (not shown) operates in conjunction with a processor to perform various tasks related to navigation within warehouse 10 as well as to navigate to fiducial markers 30 located on shelves 12. ). The fiducial marker 30 (eg, a two-dimensional bar code) corresponds to the bin/location of the ordered item. The guidance technique of the present invention is described in detail below in connection with FIGS. 4-8. Fiducial markers are also used to identify charging stations in accordance with aspects of the invention, and navigation of such charging stations to fiducial markers is the same as navigation to bins/locations of ordered items. Once the robot has moved to the charging station, more precise guidance techniques will be used to dock the robot there. Such guidance techniques are discussed below.

Referring again to FIG. 2B, the base 20 includes a top surface 32 in which a tote or bin may be stored for carrying items. Also shown is a coupling portion 34 that engages any one of a plurality of replaceable armatures 40, one of which is shown in FIG. The particular armature 40 of FIG. input device). In some embodiments, armature 40 supports one or more totes for carrying items. In other embodiments, base 20 supports one or more totes for carrying contained items. As used herein, the term "tote" refers to a cargo holder, bin, basket, shelf, pole from which items may be suspended, can, crate, shelf, stand, trestle, container, box, canister. , containers, and storage, but are not limited to these.

Although current robot technology is excellent at moving around warehouse 10, robots 18 are unable to quickly and efficiently remove items from shelves due to the technical difficulties associated with robots manipulating objects. They are not very good at picking items and placing them in the tote 44. A more efficient way to pick items is to have an on-premises operator, typically a human, perform the task of physically removing the ordered items from shelves 12 and placing the items on robot 18, such as in tote 44. 50. The robot 18 enters the premises via a tablet 48 (or laptop/other user input device) that can be read by the premises operator 50 or by sending the order to a handheld device used by the premises operator 50. The order is transmitted to the operator 50.

Upon receiving the order 16 from the order server 14, the robot 18 proceeds to a first location in the warehouse, for example as shown in FIG. The robot advances based on guidance software stored in memory and executed by a processor. The guidance software guides the laser radar 22, an internal table in memory that identifies the fiducial identification ("ID") of the fiducial marker 30 that corresponds to the location within the warehouse 10 where a particular item can be found, and It relies on data about the environment collected by the cameras 24a and 24b for the purpose.

Upon arriving at the correct location (pose), the robot 18 parks itself in front of the shelf 12 where the item is stored and waits for the on-site operator 50 to remove the item from the shelf 12 and place it into the tote 44. wait. If the robot 18 has other items to retrieve, it proceeds to that location. The items removed by robot 18 are then sent to processing station 100 of FIG. 1 where they are packaged and shipped. Although the processing station 100 has been described with respect to this illustration as capable of guiding and unloading/packing robots, it is also possible that the robot is configured to either guide or unload/pack at the station. It's okay. That is, the robot may be limited to performing a single function.

Those skilled in the art will appreciate that each robot may be fulfilling one or more orders, and each order may consist of one or more items. Typically, some form of route optimization software will be included to increase efficiency, but this is beyond the scope of this invention and is therefore not described herein.

To simplify the description of the present invention, a single robot 18 and operator 50 will be described. However, as is apparent from FIG. 1, a typical fulfillment operation involves many robots and operators working together within a warehouse to fulfill a continuous stream of orders.

The basic guidance techniques of this invention as well as the semantic mapping of the SKU of the item to be retrieved to the reference ID/pose associated with the reference marker in the warehouse in which the item is located are related to Figures 4-8. and will be explained in detail below.

One or more robots 18 must be used to create a map of the warehouse 10 and to determine the locations of various fiducial markers distributed throughout the warehouse. To do this, one or more of the robots 18 perform self-localization, a computational problem that builds or updates the robot's laser radar 22 and a map of the unknown environment while moving through the warehouse. The map 10a in FIG. 4 is constructed/updated using simultaneous localization and mapping (SLAM) with environment map creation. Common SLAM approximate solutions include particle filters and extended Kalman filters. Although the SLAM GMapping technique is the preferred technique, any suitable SLAM technique can be used.

The robot 18 utilizes the robot's laser radar 22 to move throughout the space and locate open spaces 112, walls 114, objects 116, and the like based on reflections that the laser radar receives as it scans the environment. Other static obstacles, such as shelves 12 in the space, are identified to create a map 10a of the warehouse 10.

While building map 10a (or updating map 10a thereafter), one or more robots 18 move throughout warehouse 10 using cameras 26, scanning the environment and dispersing throughout the warehouse. 3 and locates fiducial markers (two-dimensional bar codes) on shelves proximal to bins, such as 32 and 34 in FIG. 3, in which items are stored. Robot 18 uses a known starting point or origin, such as origin 110, as a reference. When the robot 18 locates a fiducial marker, such as the fiducial marker 30 of FIGS. 3 and 4, using the robot's camera 26, its location relative to the origin 110 within the warehouse is determined.

By using wheel encoders and orientation sensors, vector 120 and the robot's position within warehouse 10 can be determined. The robot 18 uses the captured image of the fiducial marker/two-dimensional bar code and its known size to determine the orientation and distance of the fiducial marker/two-dimensional bar code relative to the robot, ie, vector 130. can be judged. If vectors 120 and 130 are known, vector 140 between origin 110 and fiducial marker 30 can be determined. Determine the pose (position and orientation) of the reference marker 30 defined by the quaternion (x, y, z, ω) from the vector 140 and the determined orientation of the reference marker/two-dimensional bar code with respect to the robot 18 can do.

Reference will now be made to flowchart 200 of FIG. 5 illustrating a fiducial marker location process. This is done in the initial mapping mode when the robot 18 encounters new fiducial markers in the warehouse while performing picking, placement, and/or other tasks. At step 202, robot 18 using camera 26 captures an image and at step 204 searches for fiducial markers within the captured image. If a fiducial marker is found in the image (step 204), then in step 206 it is determined whether the fiducial marker is already stored in fiducial table 300 of FIG. 6 in memory 34 of robot 18. If the reference information is already stored in memory, the flowchart returns to step 202 to capture another image. If the reference information is not in memory, a pose is determined according to the process described above and added to the reference-to-pose lookup table 300 at step 208.

A lookup table 300, which may be stored in each robot's memory, includes, for each fiducial marker, fiducial indicia 1, 2, 3, etc., and the fiducial marker/bar code pose associated with each fiducial indicia. . A pose consists of x, y, z coordinates in the warehouse, including orientation, or a quaternion (x, y, z, ω).

Another lookup table 400 of FIG. 7, which may also be stored in each robot's memory, lists the bin locations (eg, 402a-f) within the warehouse 10, where bin locations are It is associated with the reference ID 404 of, for example, the number "11". In this example, the bin location consists of seven alphanumeric characters. The first six characters (eg, L01001) relate to the shelf location within the warehouse, and the last characters (eg, A-F) identify the individual bins at the shelf location. In this example, there are six different bin locations associated with reference ID "11". There may be one or more bins associated with each reference ID/marker.

The alphanumeric bin locations are understandable to humans, such as operator 50 of FIG. 3, because they correspond to physical locations within warehouse 10 where items are stored. However, this is meaningless for the robot 18. By mapping the location to the reference ID, robot 18 can use the information in table 300 of FIG. 6 to determine the pose of the reference ID and then move to the pose as described herein.

An order fulfillment process according to the present invention is illustrated in flowchart 500 of FIG. At step 502, order server 14 obtains an order, which may consist of one or more items to be retrieved, from warehouse management system 15. Note that the order allocation process is quite complex and is beyond the scope of this disclosure. One such order allocation process is described in commonly owned U.S. patent application Ser. and is incorporated herein by reference in its entirety. Note also that the robot can have tote arrays, one for each box or compartment, so that a single robot can fulfill multiple orders. An example of such a tote array is provided in U.S. patent application Ser. ns” explained and is incorporated herein by reference in its entirety.

Continuing to refer to FIG. 8, at step 504, the SKU number of the item is determined by warehouse management system 15, and at step 506, the location of the bin is determined from the SKU number. A list of bin locations for the order is then sent to the robot 18. At step 508, robot 18 associates the location of the bin with the reference ID, and at step 510 obtains the pose of each reference ID from the reference ID. At step 512, the robot 18 moves to a pose as shown in FIG. 3, where the operator can pick the item to be removed from the appropriate bin and place it on the robot.

Item-specific information such as the SKU number and bin location obtained by the warehouse management system 15/order server 14 may be sent to the tablet 48 of the robot 18 so that the operator 50 can Upon arrival at the marker location, one can learn about the particular item to be retrieved.

Using the SLAM map and the pose of the known fiducial ID, the robot 18 can easily move to any one of the fiducial IDs using various robot guidance techniques. A preferred approach involves establishing an initial route to the pose of the fiducial marker given knowledge of the open space 112 within the warehouse 10, as well as walls 114, shelves (such as shelves 12), and other obstacles 116. . As the robot begins to move through the warehouse using the robot's laser radar 26, it determines whether there are any obstacles, fixed or dynamic, in the robot's path, such as other robots 18 and/or operators 50. The robot's path to the pose of the reference marker is repeatedly updated. The robot replans its route approximately once every 50 milliseconds, constantly searching for the most efficient and effective path while avoiding obstacles.

Using a product SKU/reference ID to reference pose mapping technique combined with a SLAM guidance technique, both of which are described herein, the robot 18 is typically used to determine its location within the warehouse. The warehouse space can be moved very efficiently and effectively without the need to use more complex guidance techniques that require additional grid lines and intermediate reference markers.

The robot 18 can easily move to any one of the fiducials using the SLAM map and the pose of the known fiducial ID using various robot guidance techniques. A preferred approach involves establishing an initial route to the pose of the fiducial marker given knowledge of the open space 112 within the warehouse 10, as well as walls 114, shelves (such as shelves 12), and other obstacles 116. . As the robot begins to move through the warehouse using the robot's laser radar 22, it determines whether any fixed or dynamic obstacles, such as other robots 18 and/or workers 50, are in the robot's path. Iteratively updates the robot's path to the pose of the reference marker. The robot replans its route approximately every 50 milliseconds, constantly searching for the most efficient and effective path while avoiding obstacles. Self-localization of a robot in a warehouse can be achieved, for example, by many-to-many multiresolution scan matching (M3RSM) operating on a SLAM map. M3RSM is described in U.S. Patent No. 10,386,851, filed August 20, 2019, entitled "MULTI-RESOLUTION SCAN MATCHING WITH EXCLUSION ZONES," the disclosure of which is incorporated herein by reference. Incorporated. Similarly, the US Patent No. 10,429, 847, registered on October 1, 2019, in the name "Dynamic Window Approach USING OPTIMAL COLLISON AVOIDANCE COST -COST -COST -CRITIC" You can use the explanation.

FIG. 9 depicts a system diagram of one embodiment of a robot 18 for use in the robot guidance system described herein. Robotic system 600 includes a data processor 620, a data storage 630, a processing module 640, and a sensor assistance module 660. The processing modules 640 may thus include a path planning module 642 , a drive control module 644 , a map processing module 646 , a localization module 648 , and a state estimation module 650 . Sensor auxiliary module 660 may include a ranging sensor module 662, a drive train/wheel encoder module 664, and an inertial sensor module 668.

Data processor 620, processing module 640, and sensor assistance module 660 may communicate with any of the components, devices, or modules illustrated or described herein with respect to robotic system 600. Transceiver module 670 may be equipped to transmit and receive data. Transceiver module 670 can transmit and receive data and information to and from a monitoring system or to one or more other robots. The data transmitted and received may include map data, route data, search data, sensor data, location and orientation data, velocity data, processing module instructions or code, robot parameters and configurations, and operations of the robot system 600. Other necessary data may be included.

In some embodiments, the ranging sensor module 662 includes one of the following: a scanning laser, a radar, a laser rangefinder, a rangefinder, an ultrasonic obstacle detector, a stereoscopic vision system, a monocular vision system, a camera, and an imaging unit. One or more can be provided. Ranging sensor module 662 can scan the environment around the robot to determine the location of one or more obstacles to the robot. In some examples, drive train/wheel encoder 664 includes one or more sensors that encode wheel position and control the position of one or more wheels (e.g., ground-engaging wheels). and an actuator. Robotic system 600 may also include ground speed sensors, including speedometers, radar-based sensors, or rotational speed sensors. The rotation rate sensor can include a combination of an accelerometer and an integrator. A rotational speed sensor can provide the observed rotational speed to data processor 620 or any module thereof.

In some embodiments, the sensor auxiliary module 660 provides translation data, position data, including historical data over time of instantaneous measurements of velocity, translation, position, rotation, height, orientation, and inertial data. data, rotational data, height data, inertial data, and orientation data. The translational or rotational speed can be detected with reference to one or more fixed reference points or static objects in the robot's environment. Translational velocity can be expressed as an absolute velocity in a direction or as a first derivative of robot position versus time. Rotational speed can be expressed as speed in degrees or as a first derivative or angular position versus time. Translational and rotational speeds can be expressed relative to the origin 0,0 (FIG. 4) and a 0 degree direction corresponding to an absolute or relative coordinate system. Processing module 640 can use the observed translational velocity (or position versus time measurement) in combination with the detected rotational velocity to estimate the observed rotational velocity of the robot.

In some examples, locomotion by an autonomous or semi-autonomous robot requires some form of spatial model of the robot's environment. Spatial models are further described in US Pat. No. 10,386,851. Spatial models can be represented as bitmaps, maps of objects, maps of landmarks, and other forms of two-dimensional and three-dimensional digital images. A spatial model of a warehouse facility can represent a warehouse and interior obstacles such as walls, ceilings, roof supports, windows and doors, shelves and storage bins. Obstacles may be stationary, moving, such as other robots or machines operating within the warehouse, or relatively fixed, such as temporary partitions, pallets, shelves, and boxes, but may It can be something that changes as items are stored, picked, and restocked. The spatial model includes target locations, such as shelves or boxes, marked with references to which the robot can be oriented to perform tasks, or up to the location of temporary holding or charging stations. It can also be expressed. The spatial model may also include virtual obstacles and objects, such as barriers, crossing thresholds, and RFID tunnels.

In some embodiments, the robot can use the map to determine the robot's pose within the environment and plan and control the robot's movement along a path while avoiding obstacles. . Such a map may be a "local map" representing spatial features in the immediate vicinity of a robot or target location, or a "global map" representing features of an area or facility that includes the operating range of one or more robots. . The map may be provided to the robot from an external monitoring system, or the robot may construct the map using internal ranging and locating sensors. One or more robots can collaboratively map a shared environment, and the resulting map is further refined as the robots move, collect and share information about the environment. .

In some embodiments, the monitoring system includes a central server that performs monitoring of multiple robots within a manufacturing warehouse or other facility, without losing the generality of the applications of the methods and systems described herein. or the monitoring system may comprise a distributed monitoring system comprised of one or more servers operating entirely or partially remotely, on-site or off-site. The surveillance system can include one or more servers having at least a computer processor and memory to run the surveillance system, and one or more robots operating in a warehouse or other facility. One or more transceivers may further be included for communicating information. The monitoring system may be hosted on a computer server or in the cloud, and may send messages between the robot and the monitoring system via wired and/or wireless communication media, including the Internet. Communicates with the local robot by a local transceiver configured to transmit and receive.

Those skilled in the art will recognize that mapping a robot for purposes of the present invention can be performed using methods known in the art without loss of generality. Further discussion of robotic mapping methods can be found in Sebastian Thrun, "Robotic Mapping: A Survey," Carnegie-Mellon University, CMU-CS-02-111, February 2002, incorporated herein by reference. It is incorporated.

Robot Guidance Management Some guided spaces or environments, such as warehouses, can be divided into two or more zones. Such zones may include, for example, secure areas for products requiring higher security, temperature-controlled areas such as freezers, areas for specific types of goods, or areas with high security separate from adjacent areas. This may include, but is not limited to, areas of The zone may, for example, include shelves 12 filled with items to be included in the order, as explained above. The zone may be free of shelves or other obstructions, for example, to accommodate rapid movement of the robot within the environment.

Zones can be separated by physical barriers, such as fixed walls or movable partitions. Zones can be separated by virtual barriers, where no physical barriers exist. A physical barrier may include a door or other movable partition thereon. Adjacent zones at various heights may be accessible using sloped floors or elevators.

A robot guidance management system and method for enabling a robot 18 to move through an environment divided into two or more zones is described herein. FIG. 10 is a map showing a guidance space or environment 900 divided into five zones 901, 902, 903, 904, 905. It will be appreciated that the environment can be divided into any desired number and type of zones. Boundaries between adjacent zones may be defined by physical barriers, virtual barriers, or a combination thereof. As shown in FIG. 10, a first zone 901 is separated from a second zone 902 and a third zone 903 by a physical barrier, such as a wall, as indicated by solid lines 912, 914 in FIG. ing. A door 932 is provided in the wall 914 and can be opened to allow passage of a robot or human, or closed to prevent passage of a robot or human. The boundary between the second zone 902 and the third zone 903 is defined in part by a physical wall 918, shown in solid lines, and in part by a virtual barrier 918, shown in dashed lines. It is being The boundary between the third zone 903 and the fourth and fifth zones 904, 905 is defined by an imaginary barrier 922 shown in dashed lines. Similarly, the boundary between the fourth zone 904 and the fifth zone 905 is defined by an imaginary barrier 924, shown as a dashed line.

The map also shows passageways or thresholds through the boundaries through which the robot 18 or human 50 can proceed from one zone to an adjacent zone. In the example shown in FIG. 10, the door 932 of the wall 914 between the first zone 901 and the third zone 903 is located at a threshold 942 along the boundary. A virtual threshold 944 forms a virtual barrier 918 that forms the boundary between the second zone 902 and the third zone 903 and a virtual barrier that forms the boundary between the third zone 903 and the fourth zone 904. It is located in Two virtual sills 946, 948 are located in the virtual barrier 922 forming the boundary between the third zone 903 and the fifth zone 905. A sill 952, which may be an RFID tunnel to enable tracking of a robot across the sill, is located between the third zone 903 and the fifth zone 905. The threshold is not located at a physical barrier between the first zone 901 and the second zone 902 or at a virtual barrier between the fourth zone 904 and the fifth zone 905. By creating virtual barriers, warehouses can be sectioned off without the need to erect physical walls. The partition can be changed by changing the virtual barrier as necessary. Additionally, as shown, for example in the case of zone 905, it is possible to track the robot's entry into zone 905 through the RFID tunnel shown at the entrance to zone 905.

The threshold can be defined to allow passage of the robot in both directions or in only one direction. For example, sills 932 and 946 are defined to allow passage in both directions, as indicated by double-headed arrows. Threshold 952 is defined to permit passage in one direction from zone 903 to zone 905, and sill 948 is defined to permit passage in the opposite direction from zone 905 to zone 903.

At least one waypoint is associated with each threshold. In some embodiments, two waypoints are associated with each threshold. In some examples, waypoints may be defined at a distance from the boundary. In some examples, waypoints may be defined on the border along the threshold. In some embodiments, two waypoints associated with the sill may be defined that are spaced apart at locations on either side of the boundary along the sill. In some embodiments, two waypoints may define the beginning and end of a path across a sill, for example, to enable efficient unidirectional movement along the path.

Waypoints may be defined relative to origin 110, as described above with respect to FIG. Accordingly, each waypoint may be defined by at least x and y coordinates, or x, y, and z coordinates. Each robot 18 includes a look-up table stored in memory that indicates the coordinates of each waypoint, thereby allowing the robot to be guided to each waypoint. The lookup table may also include poses associated with each waypoint. The lookup table may therefore include orientations or quaternions (x, y, z, ω) as explained above. In some embodiments, fiducial markers may be associated with one or more waypoints, although fiducial markers associated with waypoints are not required for robot guidance as described herein. As described above in connection with FIG. 4, a robot equipped with the coordinates of a waypoint can use, for example, wheel encoders and orientation sensors to move to that waypoint. When the robot reaches a desired waypoint, it can orient itself to the desired pose location associated with that waypoint.

To manage such navigation, the warehouse management system server or order server may include a map 900, as shown in FIG. Each robot 18 that wishes to move within the environment communicates with the server. Generally, as long as each robot 18 is operating within the guided space, the robots can operate to perform one or more tasks of the ordered task list, as described above. Each robot can determine, based on a predetermined task list, an optimized route that may require the robot to cross a threshold, as described above. The robot may utilize, for example, the path planning module 642 and pathfinder algorithm described above.

In some examples, the robot may be configured to pass through waypoints and cross thresholds without stopping. In some examples, the robot may be configured to pause upon reaching the waypoint before crossing the threshold. In some embodiments, after pausing at the waypoint and before crossing the threshold, the robot uses, for example, a camera, laser detector, or radar detector, or a combination thereof, as described above. You can determine whether there is traffic at the threshold. In some examples, upon arrival at the waypoint, the robot may receive further instructions or commands from the robot monitoring server regarding whether to cross the threshold. Such instructions or commands may be pushed automatically from the server or upon request from the robot. Requiring a waypoint pass or pause of the robot controls the guidance of the robot across a threshold that directs the robot to pass across a boundary (physical or virtual) of a zone.

In some examples, the robot may be configured to join a queue of robots waiting to cross the threshold. For example, another robot may already be paused at the pose that defines the waypoint. Also, one or more other robots may be waiting at the queue location to also cross the threshold at the appropriate time. The newly arrived robot joins a slot or location in the queue that is offset from the pose location of the waypoint and/or offset from the pose location of other robots waiting in the queue to cross the threshold. be able to. The robot's queuing may be controlled by the guidance server or the warehouse management server 15, for example.

For example, when one or more robots attempts to move into a space occupied by another robot, an alternate destination for the robot is generated to queue the robot and avoid the occurrence of a "race condition". . When another robot attempts to move into the occupied space, the robot is redirected to a temporary holding location or queue slot that is offset from the occupied pose. The queue slot locations may be non-uniform and variable given the dynamic environment of the warehouse. The queue slots can be staggered according to a queuing algorithm that observes the underlying global map as well as existing obstacles and constraints in the local map. The queuing algorithm allows queuing in a space close to the target location/pose to avoid blocking traffic, obstructing other locations, and creating new obstacles. Practical limitations can also be taken into account.

In addition, robots can be managed to enter queue slots appropriately, such that a robot with first priority for occupying a pose can enter the first queue slot. In contrast, other robots enter slots in other queues based on their priorities. Priority may be determined by the order in which the robot enters the zone in proximity to the pose. When a robot moves from a pose (a target location), the next robot moves from one slot in the queue to the pose, and any other robot can advance to the position of each slot in the queue. Therefore, the way to guide the robot to the queue slot and ultimately to the target location is by temporarily turning the robot from the target location pose to the queue slot pose. achieved. In other words, if it is determined that the robot should be placed in a queue slot, the robot's target pose is temporarily adjusted to the pose that corresponds to the queue slot location to which the robot is assigned. be done. As the robot advances its place in the queue, the pose is prioritized to the next priority until the robot can reach the original target location, at which time the pose is reset to the original target pose. Temporarily adjusted again to pose high queue slots. Queuing robots are further described in U.S. Pat. Incorporated into the specification.

In some examples, a route may require the robot to move to a zone at a different height than the height of an adjacent zone. In some examples, the sill can cross the slope or ramp between zones. In some examples, depending on the degree of slope, two waypoints may define the start and end points of a path along the slope across the sill. In some embodiments, an elevator may be provided to transport the robot from one zone to another. The robot can arrive at a waypoint associated with an elevator, and can issue requests and/or commands to call the elevator and open the elevator doors, which causes the robot to enter the elevator, and then exit the elevator. The elevator door can define a threshold so that it can be directed into the zone.

As a further explanation, if the virtual barrier does not have a defined threshold, the robot may determine that a route passing near the edge of the physical barrier is the shortest route to the destination. For example, robot 18', shown in dashed lines in FIG. 9, is shown passing close to the edge of a wall and taking a shorter, more efficient route. However, shorter routes may result in more congestion or otherwise undesirable conditions. Thus, in this case, by defining a threshold and an associated waypoint at a predetermined location further spaced along the boundary from the edge of the wall, the robot 18' either passes through the waypoint of the threshold or Or you will be forced to take a route that temporarily stops at the threshold way point. Thus, the less desirable but perhaps more likely route that the robot would normally take is avoided.

The server can track the activities of robots and/or human workers within the warehouse, such as the warehouse management system 15, the order server 14, a standalone server, a network of servers, the cloud, the processor and memory of the robot's tablet 48, etc. , the processor and memory of the base 20 of the robot 18, the tablet 48 of the robot, and/or the base 20, including a distributed system comprising memory and processors. In some embodiments, waypoint information can be automatically pushed from robot monitoring server 902 to robot 18. In other embodiments, waypoint information may be sent in response to a request from robot 18.

Therefore, the guidance management system and method can advantageously guide a robot more efficiently and with lower risk of collision through a guidance space that is divided into zones, reducing the inefficiency of the robot's task completion. Delays can be prevented.

Non-Limiting Exemplary Computer Processing Device FIG. 10 shows an example computer processing device 1210, or computer processing device, that may be used in accordance with the various embodiments described above with reference to FIGS. 1-9. It is a partial block diagram. Computer processing device 1210 includes one or more non-transitory computer-readable media that store one or more computer-executable instructions or software for implementing the example embodiments. Non-transitory computer-readable media includes one or more types of hardware memory, non-transitory tangible media (e.g., one or more magnetic storage disks, one or more optical disks, one or more flash drives), but are not limited to these. Memory 1216 included in computer processing device 1210 may, for example, store computer-readable and computer-executable instructions or software for performing the operations disclosed herein. The memory may store a software application 1240 that is programmed to perform the various disclosed operations discussed in connection with FIGS. 1-9, for example. Computer processing device 1210 includes a configurable and/or programmable processor for executing computer-readable and computer-executable instructions or software stored in memory 1216 and other programs to control system hardware. 1212 and associated core 1214, and optionally one or more additional configurable and/or programmable processing devices, such as processor 1212' and associated core 1214' (e.g., having multiple processors/cores). (for computing devices) may also be included. Processor 1212 and processor 1212' may each be a single core processor or a multi-core (1214 and 1214') processor.

Virtualization may be used in computing device 1210 so that infrastructure and resources within the computing device can be dynamically shared. Virtual machine 1224 may be provided to handle processes running on multiple processors so that the process appears to be using only one computing resource rather than multiple computing resources. It is also possible to use multiple virtual machines with one processor.

Memory 1216 may include computing device memory or random access memory such as, but not limited to, DRAM, SRAM, EDO RAM, and the like. Memory 1216 may also include other types of memory, or combinations thereof.

A user interacts with a computer processing device 1210 through a visual display device 1201, 111A-D, such as a computer monitor, that can display one or more user interfaces 1202, which may be implemented according to an example embodiment. can do. Computer processing device 1210 may include other I/O devices for receiving input from a user, such as a keyboard or any suitable multi-point touch interface 1218, pointing device 1220 (eg, a mouse). A keyboard 1218 and pointing device 1220 may be coupled to visual display device 1201. Computer processing device 1210 may include other suitable conventional I/O peripheral devices.

Computer processing device 1210 includes a hard drive, CD-ROM, or other computer-readable medium for storing data and computer-readable instructions and/or software to perform the operations disclosed herein. One or more storage devices 1234 may also be included, including but not limited to. The example storage device 1234 may also store one or more databases that store any suitable information necessary to implement the example embodiments. The database may be updated manually or automatically at any suitable time to add, delete, and/or update one or more items in the database.

The computing device 1210 may be connected to one or more networks, such as a local area network (LAN), a wide area network (WAN), or a network via one or more network devices 1232. Standard telephone lines, LAN or WAN links (e.g. 802.11, T1, T3, 56kb, X.25), broadband connections (e.g. ISDN, Frame Relay, ATM), wireless connections, controller area networks (CAN). A network interface 1222 may be included that is configured to interface with the Internet via a variety of connections, including, but not limited to, an Internet connection area network), or some combination of any or all of the above. . Network interface 1222 may include an embedded network adapter, network interface card, PCMCIA network card, card bus network adapter, wireless network adapter, USB network adapter, modem, or computing device 1210. , any other device suitable for interfacing with any type of network capable of communicating and performing the operations described herein. Additionally, computing device 1210 can be a workstation, desktop computer, server, laptop, handheld computer, tablet computer, or any computer capable of communication and sufficient to perform the operations described herein. The computing device may be any computing device, such as any other form of computing or telecommunications device, that has significant processor power and memory capacity.

Computer processing device 1210 can run any version of the Microsoft® Windows® operating system (Microsoft, Redmond, Wash.), various releases of Unix and Linux® operating systems, or a Macintosh computer. Any version of the MAC OS® (Apple, Inc., Cupertino, Calif.) operating system, any embedded operating system, any real-time operating system, any open source operating system , any proprietary operating system, or any other operating system capable of running on a computer processing device and performing the operations described herein. I can do it. In an exemplary embodiment, operating system 1226 may be run in native mode or emulation mode. In an exemplary embodiment, operating system 1226 may be run on one or more cloud machine instances.

FIG. 11 is a block diagram of an exemplary computing device in some distributed embodiments. 1-9, and portions of the above example discussion, refer to warehouse management system 15, order server 14, or robot tracking server 902, each running on separate or common computing devices. However, instead, any of the warehouse management system 15, order server 14, or robot guidance server may be connected to separate server systems 1301a-d over a network 1305, and in some cases to kiosks, desktops, etc. It will be appreciated that it may be distributed to user systems such as computing device 1302 or portable computing device 1303. For example, order server 14 may be distributed among tablets 48 of robot 18. In some distributed systems, the warehouse management system software and/or order server software modules may be located separately on server systems 1301a-d and communicated via network 1305. can communicate with each other.

While the foregoing description of the invention is provided to enable one skilled in the art to make and use what is presently believed to be the best mode thereof, one skilled in the art will appreciate the specific examples and examples herein. Variations, combinations, and equivalents will be understood and appreciated. The embodiments of the invention described above are intended to be illustrative only. Those skilled in the art may make changes, modifications, and variations to the particular embodiments without departing from the scope of the invention, which is defined solely by the claims appended hereto. Therefore, the invention is not limited to the embodiments and examples described above.

Having thus described the invention and its preferred embodiments, what is claimed as new and is protected by Letters Patent is the following.

Claims (25)

A method for guiding an autonomous robot from a first zone in an environment to an adjacent second zone, the method comprising:
by a server, the first zone and the second zone in the environment, a threshold along a boundary between the first zone and the second zone, and a waypoint associated with the threshold; a step of defining
determining a route for the autonomous robot from the first zone to the second zone across the threshold, the route including the waypoint; and A method comprising guiding the robot along the route from the first zone to the second zone, including passing through the waypoint in conjunction with crossing the threshold. 2. The method of claim 1, wherein the waypoint is defined by a waypoint pose, and the step of determining a route includes determining a route segment to the waypoint pose. The step of passing through the way point is passing through the way point pose without pausing at the way point pose, or pausing at the way point pose before crossing the threshold. 3. The method of claim 2, comprising the step of: 2. The method of claim 1, wherein the waypoint is located at a distance from the sill or on the boundary along the sill. The method of claim 1, further comprising defining, by the server, a second waypoint associated with the threshold, the waypoint and the second waypoint being located on opposite sides of the threshold. . 2. The method of claim 1, wherein the boundary between the two adjacent zones is a physical barrier, and the sill is located at an opening in the physical barrier. 2. The method of claim 1, wherein the boundary between the two adjacent zones is a virtual barrier, and the threshold is a location defined along the virtual barrier. 2. The method of claim 1, further comprising defining by the server a second threshold along the boundary between the adjacent zones, a second waypoint associated with the second threshold. defining, by the server, the threshold allowing passage of the robot in a first direction; and passage of the robot in a direction opposite to the first direction along the boundary between the adjacent zones; 2. The method of claim 1, further comprising: defining a second threshold to allow access. 2. The method of claim 1, further comprising the step of the robot joining a queue of robots waiting to pass through the threshold. 2. The method of claim 1, further comprising the step of the robot detecting obstacles at the threshold using a camera, laser detector, or radar detector, or a combination thereof. 2. The method of claim 1, wherein each of the zones is a secure area, a temperature controlled area, a warehouse area, or an area at a different height than an adjacent area, or a combination thereof. A system for guiding an autonomous robot from a first zone to an adjacent second zone within an environment, the system comprising:
defining the first zone and the second zone in the environment, a threshold along a boundary between the first zone and the second zone, and a waypoint associated with the threshold; an autonomous robot in communication with the server, the robot comprising a processor and a memory, the memory being executed by the processor to cause the robot to:
determining a route including the way point from the first zone to the second zone that crosses the threshold, and passing through the way point in conjunction with crossing the threshold; A system storing instructions for guiding the robot along the route from a first zone to the second zone. the waypoint is defined by a waypoint pose, the memory further storing instructions that, when executed by the processor, cause the autonomous robot to determine a route segment to the waypoint pose; 14. The system of claim 13. The memory, when executed by the processor, causes the robot to move through the waypoint pose without pausing in the waypoint pose or before crossing the threshold. 14. The system of claim 13, further storing instructions to pause in a pause. 14. The system of claim 13, wherein the waypoint is located at a distance from the sill or on the boundary along the sill. 14. The system of claim 13, wherein the server is configured to define a second waypoint associated with the sill, the waypoint and the second waypoint being located on opposite sides of the sill. 14. The system of claim 13, wherein the boundary between the two adjacent zones is a physical barrier, and the sill is located at an opening in the physical barrier. 14. The system of claim 13, wherein the boundary between the two adjacent zones is a virtual barrier, and the threshold is a location defined along the virtual barrier. 14. The server is configured to define a second threshold along the boundary between the two adjacent zones and a second waypoint associated with the second threshold. system described in. The robot guidance server defines the threshold that allows passage of the robot in a first direction, and the robot guidance server defines the first threshold along the boundary between the first zone and the second zone. 14. The system of claim 13, configured to define a second threshold that allows passage of the robot in a direction opposite to that of the second threshold. 14. The system of claim 13, wherein the memory further stores instructions that, when executed by the processor, cause the autonomous robot to join a queue of robots waiting to pass through the threshold. The memory further stores instructions that, when executed by the processor, cause the autonomous robot to detect obstacles at the threshold using a camera, laser detector, or radar detector, or a combination thereof. 14. The system of claim 13. 14. The system of claim 13, wherein each of the zones is a secure area, a temperature controlled area, a warehouse area, or an area at a separate height from adjacent areas, or a combination thereof. 12. The server further comprises one or more of a warehouse management system, an ordering server, a stand-alone server, a distributed system comprising the memory of at least two of the plurality of robots, or a combination thereof. The system according to item 13.

Images